# VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation

arXiv: https://arxiv.org/abs/2511.15200 · HTML: https://mlsanity.com/paper/2511.15200/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2025.

## Built on by (most cited first, 25 of 25)

- [TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control](https://mlsanity.com/paper/2602.07439/) (2026)
- [Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation](https://mlsanity.com/paper/2602.15828/) (2026)
- [Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations](https://mlsanity.com/paper/2602.06643/) (2026)
- [HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation](https://mlsanity.com/paper/2604.07993/) (2026)
- [NavDreamer: Video Models as Zero-Shot 3D Navigators](https://mlsanity.com/paper/2602.09765/) (2026)
- [SteadyTray: Learning Object Balancing Tasks in Humanoid Tray Transport via Residual Reinforcement Learning](https://mlsanity.com/paper/2603.10306/) (2026)
- [SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.22894/) (2026)
- [LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition](https://mlsanity.com/paper/2606.11628/) (2026)
- [DeFM: Learning Foundation Representations from Depth for Robotics](https://mlsanity.com/paper/2601.18923/) (2026)
- [Learning Human-Like Badminton Skills for Humanoid Robots](https://mlsanity.com/paper/2602.08370/) (2026)
- [SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating](https://mlsanity.com/paper/2603.23983/) (2026)
- [SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework](https://mlsanity.com/paper/2605.20373/) (2026)
- [Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds](https://mlsanity.com/paper/2603.18532/) (2026)
- [LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World](https://mlsanity.com/paper/2606.01458/) (2026)
- [Trust-Region Diffusion Policies for Massively Parallel On-Policy RL](https://mlsanity.com/paper/2606.15260/) (2026)
- [CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation](https://mlsanity.com/paper/2606.23680/) (2026)
- [HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping](https://mlsanity.com/paper/2602.16705/) (2026)
- [ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors](https://mlsanity.com/paper/2603.15956/) (2026)
- [SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds](https://mlsanity.com/paper/2604.08544/) (2026)
- [Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing](https://mlsanity.com/paper/2604.09499/) (2026)
- [Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions](https://mlsanity.com/paper/2609.16683/) (2026)
- [Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation](https://mlsanity.com/paper/2605.28812/) (2026)
- [VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich Manipulation](https://mlsanity.com/paper/2605.29564/) (2026)
- [ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids](https://mlsanity.com/paper/2609.15988/) (2026)
- [A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control](https://mlsanity.com/paper/2610.12465/) (2026)

## Abstract (arXiv)

A key barrier to the real-world deployment of humanoid robots is the lack of autonomous loco-manipulation skills. We introduce VIRAL, a visual sim-to-real framework that learns humanoid loco-manipulation entirely in simulation and deploys it zero-shot to real hardware. VIRAL follows a teacher-student design: a privileged RL teacher, operating on full state, learns long-horizon loco-manipulation using a delta action space and reference state initialization. A vision-based student policy is then distilled from the teacher via large-scale simulation with tiled rendering, trained with a mixture of online DAgger and behavior cloning. We find that compute scale is critical: scaling simulation to tens of GPUs (up to 64) makes both teacher and student training reliable, while low-compute regimes often fail. To bridge the sim-to-real gap, VIRAL combines large-scale visual domain randomization over lighting, materials, camera parameters, image quality, and sensor delays--with real-to-sim alignment of the dexterous hands and cameras. Deployed on a Unitree G1 humanoid, the resulting RGB-based policy performs continuous loco-manipulation for up to 54 cycles, generalizing to diverse spatial and appearance variations without any real-world fine-tuning, and approaching expert-level teleoperation performance. Extensive ablations dissect the key design choices required to make RGB-based humanoid loco-manipulation work in practice.